Back to article
thinkingmachines.ai

Defeating Nondeterminism in LLM Inference (opens in new tab)

Covered by 8 sources See all sources covering this story including Quarkslab's blog, DEV CommunityDiscussed on DEV

Covered in 9 articles

Quarkslab's blog·

From prompt to pwned: chaining LLM and web bugs to Admin

Discussed on Hacker News
Feeds
DEV Community·

Same Weights, Same Prompt, Different Triage Level

Discussed on DEV
Feeds
DEV Community·

Why Your LLM Agent Gives a Different P-Value Every Time (And What to Build Instead)

Discussed on DEV
Feeds
thehumanoid.ai·

KinetIQ Ascend: Toward 100% Reliable Manipulation and Superhuman Speed

Discussed on Hacker News
Feeds
zansara.dev·

Setting the temperature to zero will make an LLM deterministic?

Discussed on Hacker News
Feeds
Datanalyst·

Finding Real AI Use-Cases in the Token Era

Feeds
sixsideddice.com·

Sideways, Not Up: Why AI Is Not a New Abstraction Layer

Discussed on Hacker News
Feeds
Abacus Noir·

Chasing Bit-Equality Through a Wasm Actor Runtime

Feeds
altimate.ai·

The Correctness Layer: How We Beat Claude Code on the ADE Benchmark

Discussed on Hacker News
Feeds

Keyboard Shortcuts

Navigation

Next / previous post
j/k
Open post
oorEnter
Preview post
v

Post Actions

Love post
a
Like post
l
Dislike post
d
Undo reaction
u
Save / unsave
s

Recommendations

Add interest / feed
Enter
Not interested
x

Go to

Home
gh
Interests
gi
Feeds
gf
Likes
gl
History
gy
Changelog
gc
Settings
gs
Discover
gb
Search
/

General

Show this help
?
Submit feedback
!
Close modal / unfocus
Esc

Press ? anytime to show this help